Antonio Andrade Marin, Salim Busaidy, Mohammed Ahsan Adib Murad, Issa Al Balushi ¡ 19 authors
Abstract A failed Electrical Submersible Pump (ESP) well is generally identified when there is no flow to the surface. The process of reviving well production can take weeks leading to huge unwanted deferment. Through a Proof-Of-Concept (PoC), the objective is to prototype and evaluate the results of an early failure detection for ESP wells using Machine Learning (ML), without reserving focus on implementation. By demonstrating the feasibility of this approach and verifying that the concept has practical potential, the tool can be used to reduce deferment and identify failure prone component to either devise mitigation strategy for extending time-to-failure or work on an improved design before failure. The paper details all the work undertaken to develop a Predictive Analytics model based on ML algorithms using field sensor data, real time physics-based model calculated data and well failure history to predict ESP well failure and identify failed component in advance. The approach of database standardization, data pre-processing, machine-learning algorithm selection, supervised training and validation dataset creation shall be discussed. ESP domain knowledge used for Feature Engineering across multiple modeling iterations to consistently improve well and component level model metrics shall be detailed. After the evaluation by well owners at Petroleum Development Oman (PDO), refered as Operator's blind test, the prediction of the ML algorithm shows a good accuracy in its ability to capture historical failures ranging between days to months in advance. The Well Level Failure model captures failure prone wells with a precision of 90% and accuracy of 76%. The Component Level Failure model correctly identifies pump failure from other failures with a precision of 92% and accuracy of 88%. These numbers show the reliability of future predictions that could enable users to make high stake workover and operating envelope optimization decisions with confidence. Following benefits are estimated from both Well failure and Pump Component failure prediction models metrics respectively: 28.35% savings from total unscheduled ESP deferment1% increase in Overall Mean Time to Failure (MTTF) based on optimization of predicted pump component failure wells. In an organization where over thousand ESP wells are managed by limited production engineers, post ESP failure, the effort invested for hoist scheduling, raising new well proposal, rig mobilization, new ESP installation and commissioning utilizes huge time and leads to long undesired oil deferment. Implementation of engineered analytics to predict ESP failures and failed components in advance can support production engineers to plan early for workover operations, increase well run life and minimize oil deferment losses. Methodologically assessed by Senior Petroleum Engineers in selected clusters (using historical data and in the context of each failure and non-failure cases), the Predictive Analytics journey has started. It is ready to be operationalized at a small scale to build confidence as an advisory tool for Production Engineers in real-time to evaluate multiple wellsâ failure probability on a daily basis and generate massive savings from well deferment. This agile journey focused on value generation is achieved with combined efforts between technology, domain knowledge and data.
Subhash Ayirala, Ali AlâYousef, Zuoli Li, Zhenghe Xu
Summary Smart waterflooding (SWF) through tailoring of injection-water salinity and ionic composition is receiving favorable attention in the industry for both improved and enhanced oil recovery (EOR) in carbonate reservoirs. Surface/intermolecular forces, thin-film dynamics, and capillary/adhesion forces at rock/fluid interfaces govern crude-oil liberation from pores. On the other hand, stability and rigidity of oil/water interfaces control the destabilization of interfacial film to promote coalescence between released oil droplets and to improve the oil-phase connectivity. As a result, the dynamics of oil recovery in smart waterflood is caused by the combined effect of favorable interactions occurring at both oil/brine and oil/brine/rock interfaces across the thin film. Most of the laboratory studies reported so far have been focused on only studying the interactions at rock/fluid interfaces. However, the other important aspect of characterizing water ion interactions at the crude oil/water interface and their impact on film stability and oil-droplet coalescence remains largely unexplored. A detailed experimental investigation was conducted to understand the effects of different water ions at the crude-oil/water interface by using several instruments such as Langmuir trough, interfacial shear rheometer, Attension tensiometer, and coalescence time-measurement apparatus. The reservoir crude oil and four different water recipes with varying salinities and individual ion concentrations were used. Interfacial tension (IFT), interface pressures, compression energy, interfacial viscous and elastic moduli, oil-droplet crumpling ratio, and coalescence time between crude-oil droplets are the major experimental data measured. The IFTs are found to be the largest for deionized (DI) water, followed by the 10-times-reduced-salinity seawater and 10-times-reduced-salinity seawater enriched with sulfates. Interfacial pressures gradually increased with compressing surface area for all the brines and DI water. The compression energy (integration of interfacial pressure over the surface-area change) is the highest for DI water, followed by the lower-salinity brine containing sulfate ions, indicating rigid interfaces. The transition times of interfacial layer to become elastic-dominant from viscous-dominant structures are found to be much shorter for brines enriched with sulfates, once again confirming the rigidity of interface. The crumpling ratios (oil drop wrinkles when contracted) are also higher with the two recipes of DI water and sulfates-only brine to indicate the same trend and to confirm elastic rigid skin at the interface. The coalescence time between oil droplets was the least in brines containing sufficient amounts of magnesium and calcium ions, while the highest in DI water and sulfate-rich brine, respectively. These results, therefore, showed a good correlation of coalescence times with the rigidity of oil/water interface, as interpreted from different measurement techniques. This study, thereby, integrates consistent results obtained from different measurement techniques at the crude-oil/water interface to demonstrate the importance of both salinity and certain ions, such as magnesium and calcium, on crude-oil-droplets coalescence, and to improve oil-phase connectivity in smart waterflood.